March 5, 2024, 2:53 p.m. | Aleem Khan, Andrew Wang, Sophia Hager, Nicholas Andrews

cs.CL updates on arXiv.org arxiv.org

arXiv:2312.17242v2 Announce Type: replace
Abstract: Prior work in style-controlled text generation has focused on tasks such as emulating the style of prolific literary authors, producing formal or informal text, and mitigating toxicity of generated text. Plentiful demonstrations of these styles are available, and as a result modern language models are often able to emulate them, either via prompting or discriminative control. However, in applications such as writing assistants, it is desirable for language models to produce text in an author-specific …

abstract arxiv authors controlled text generation cs.cl generate generated language language models modern prior prolific style tasks text text generation toxicity type work writing

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Principal Data Engineering Manager

@ Microsoft | Redmond, Washington, United States

Machine Learning Engineer

@ Apple | San Diego, California, United States